Stacked Optimized Ensemble Machine Learning Model for Predicting Stock Trends through Candlestick Chart Analysis with Feature Engineering Approach

International Journal of Electronics and Communication Engineering

© 2024 by SSRG - IJECE Journal

Volume 11 Issue 6

Year of Publication : 2024

Authors : R. Sumathi, S. Ashokkumar

10.14445/23488549/IJECE-V11I6P107

How to Cite?

R. Sumathi, S. Ashokkumar, "Stacked Optimized Ensemble Machine Learning Model for Predicting Stock Trends through Candlestick Chart Analysis with Feature Engineering Approach," SSRG International Journal of Electronics and Communication Engineering, vol. 11,  no. 6, pp. 74-87, 2024. Crossref, https://doi.org/10.14445/23488549/IJECE-V11I6P107

Abstract:

The process of predicting stock trends through the analysis of Candlestick Charts (CCs) involves interpreting the patterns formed by these candlesticks to make informed predictions about future price movements. Utilizing Machine Learning (ML) for Stock Trend Prediction (STP) through CC analysis is common in algorithmic trading. CCs provide crucial information about the high, open, closed, and low prices within a specific time rate. However, stacked ensemble methods are employed to enhance reliability and stability, which combine the predictions of multiple models. Motivated by this objective, this work introduces the Stacked Optimized Ensemble ML Techniques with a Feature Engineering Approach for STP, referred to as SOEMLT-FEA. In the training phase, various models, including Random Forests (RF), SVM (Support Vector Machine), XGBoost, Decision Tree (DT), Adaboost, and ANN (Artificial Neural Network), are trained and optimized using the Chiroptera Algorithm (CA) to fine-tune their parameters. The optimized classifiers are then ranked, and the top three models are selected as the base classifiers for a stacking ensemble method. The efficacy of the developed feature engineering approach is confirmed by the experiential outcomes obtained (2000 and 2017) in China’s stock market. This approach demonstrates promising economic returns for individual portfolios and stocks, achieving a prediction accuracy exceeding 90% for specific trend patterns.

Keywords:

Stock trends, Candlestick chart, Future price movements, Stacked ensemble machine learning methods, Feature engineering scheme, Chiroptera algorithm.

References:

[1] Veliota Drakopoulou, “A Review of Fundamental and Technical Stocks Analysis Techniques,” Journal of Stock & Forex Trading, vol. 5, no. 1, pp. 1-8, 2016.
[Google Scholar] [Publisher Link]
[2] Divyanshu Bathla, Ashish Garg, and Sarika, “Stock Trend Prediction Using Candlestick Pattern,” Cybersecurity and Evolutionary Data Engineering, pp. 235-246, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Peter R. Cox, Technical Analysis, Cambridge University, pp. 1-179, 2011.
[Publisher Link]
[4] Michael C. Thomsett, Bloomberg Visual Guide to Candlestick Charting, John Wiley & Sons, 2012.
[Google Scholar] [Publisher Link]
[5] Candlestick Chart Patterns, Incredible Charts, [Online]. Available: https://www.incrediblecharts.com/candlestick_patterns/candlestickpatterns.php
[6] Piyapas Tharavanij, Vasan Siraprapasiri, and Kittichai Rajchamaha, “Profitability of Candlestick Charting Patterns in the Stock Exchange of Thailand (SET),” Sage Open, vol. 7, no. 4, pp. 1-18, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Nikitas Goumatianos, Ioannis T. Christou, and Peter Lindgren, “Useful Patterns Mining on Time Series: Application in the Stock Markets,” Proceeding of the 2nd International Conferences on Patterns Recognitions Application and Method, Barcelona, Spain, vol. 20, pp. 608-612, 2013.
[Google Scholar] [Publisher Link]
[8] Min Zhu, Said Atri, and Eyub Yegen, “Are Candlesticks Trading Strategies Effective in Certain Stocks with Distinct Features?,” PacificBasin Finance Journal, vol. 37, pp. 116-127, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Tsung-Hsun Lu, Yi-Chi Chen, and Yu-Chin Hsu, “Trend Definitions or Holding Strategy: What Determine the Profitability of Candlesticks Charting?,” Journal of Banking & Finance, vol. 61, pp. 172-183, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Yoshihisa Udagawa, “Designs and Implementations of Candlestick Charts Retrieval Algorithms for Predicting Stocks Price Trends,” The Fourth International Conferences on Big Data, Small Data, Linked Data and Open Data (ALLDATA 2018), pp. 19-25, 2018.
[Google Scholar] [Publisher Link]
[11] Yoshihisa Udagawa, “Predicting Stocks Price Trend using Candlestick Charts Blending Techniques,” IEEE International Conferences on Big Data (Big Data), Seattle, WA, USA, pp. 4162-4168, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Luca Cagliero, Jacopo Fior, and Paolo Garza, “Shortlisting Machine Learning-Based Stocks Trading Recommendation using Candlesticks Pattern Recognitions,” Expert System with Application, vol. 216, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Mengxia Liang et al., “A Stock Time Series Forecasting Approach Incorporating Candlestick Patterns and Sequence Similarity,” Expert Systems with Applications, vol. 205, pp. 1-26, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[14] M. Ananthi, and K. Vijayakumar, “Stock Markets Analysis Using Candlesticks Regressions and Market Trends Predictions (CKRM),” Journal of Ambient Intelligence and Humanized Computing, vol. 12, no. 5, pp. 4819-4826, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Peipei Liu et al., “Multi-Type Data Fusion Frameworks Based on Deep Reinforcement Learning for Algorithmic Trading,” Applied Intelligence, vol. 53, no. 2, pp. 1683-1706, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[16] Armin Mahmoodi et al., “A Developed Stocks Price Forecasting Model using Support Vector Machines Combined with Metaheuristic Algorithm,” OPSEARCH, vol. 60, no. 1, pp. 59-86, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Atharva Shah et al., “A Stock Market Trading Framework Based on Deep Learning Architecture,” Multimedia Tools and Application, vol. 81, no. 10, pp. 14153-14171, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Kietikul Jearanaitanakij, and Bundit Passaya, “Predicting Short Trends of Stock by Using Convolutional Neural Networks and Candlesticks Pattern,” 4th International Conferences on Information Technology (InCIT), Bangkok, Thailand, pp. 159-162, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Yaohu Lin et al., “Stock Trends Predictions using Candlesticks Charting and Ensemble Machine Learning Technique with a Novelty Features Engineering Schemes,” IEEE Access, vol. 9, pp. 101433-101446, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Lili Yin et al., “Research on Stock Trends Prediction Methods Based on Optimized Random Forests,” CAAI Transactions on Intelligence Technology, vol. 8, no. 1, pp. 274-284, 2023.
[CrossRef] [Publisher Link]
[21] Yuling Lin, Haixiang Guo, and Jinglu Hu, “An SVM-Based Approach for Stock Markets Trend Predictions,” The 2013 International Joint Conferences on Neural Network (IJCNN), Dallas, TX, USA, pp. 1-7, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[22] Luca Di Persio, and Oleksandr Honchar, “Artificial Neural Network Architecture for Stocks Price Predictions: Comparison and Application,” International Journal of Circuits, Systems and Signal Processing, vol. 10, pp. 403-413, 2016.
[Google Scholar] [Publisher Link]
[23] Rupesh A. Kamble, “Short and Long-Term Stock Trends Predictions Using Decision Trees,” International Conferences on Intelligent Computing and Control Systems, (ICICCS), Madurai, India, pp. 1371-1375, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Lokesh Kumar et al., “A Hybrid Machine Learning System for Stock Markets Forecasting,” Journal of International Technology and Information Management, vol. 20, no. 1, pp. 39-48, 2011.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Xin-She Yang, and Xingshi He, “Bat Algorithm: Literature Review and Applications,” International Journal of Bio-inspired Computation, vol. 5, no. 3, pp. 141-149, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Adán Godínez-Bautista et al., “Bio-Inspired Metaheuristics for Hyper-Parameters Tuning of Support Vector Machine Classifier,” Fuzzy Logic Augmentations of Neural and Optimization Algorithms: Theoretical Aspects and Real Application, pp. 115-130, 2018.
[CrossRef] [Google Scholar] [Publisher Link]